Wiss. Rechnen » News EN
 

Dear cluster users,

The compute cluster HoRUS and other computing systems located at and operated by the University of Siegen are financed at public expense and are liable to report on their scientific contribution.

We rely on your assistance and kindly ask you to send us a list of all publications and projects since 2012 that made use of the University’s computing resources, by July 21. 
Please also include Bachelor and Master theses, submitted publications, other papers at conferences and scientific events, and collect contributions from colleagues who are no longer using the compute resources or left the university already. If you received consulting or assistance from the HPC team in running or improving your jobs, please mark those publications accordingly.

Best regards,
Your HPC Team

Aktualisiert um 11:27 am 3. July 2020 von Jan Steiner

Dear cluster users,

the next Linux introduction course will be held on July 21, 2020 and take all day. It will be a virtual course using Zoom. For further information as well as how to register see this link.

Best regards
Your HPC team

Aktualisiert um 9:42 am 1. July 2020 von Jan Steiner

Dear users,

as part of the NRW-wide HPC competence network hpc.nrw (https://hpc.dh.nrw), and in order to further improve our support for you in the future, we kindly ask you to fill out the following survey:

https://hpc.dh.nrw/nutzerbefragung

The survey is about your current problems, needs and interests as users of our and other HPC systems. We would be very grateful if you could fill it out before June 26nd, 2020. The survey is anonymous, in English, and takes about 15 minutes to complete. Please feel free to forward this announcement to other users or potential future users.

Best regards

Your HPC Team

Aktualisiert um 10:25 am 16. June 2020 von Jan Steiner

Dear cluster users,

on June 9, 2020 our new course will be held for the first time. It is titled “MATLAB – Parallelization, Performance, Debugging”. The course will be held in German and take all day.

This is not a MATLAB introduction course! It will cover the cluster-specific aspects of using MATLAB.

The course is aimed at MATLAB users who want to use MATLAB on the cluster, parallelize their code or improve its performance.

More information about course topics and registration (in German) can be found here. All our courses are held once per semester, alternating between German and English.

Best regards
Your HPC Team

Aktualisiert um 17:22 am 20. May 2020 von Jan Steiner

Dear cluster users,

due to several security incidents at other HPC centers we have deactivated login with password from the internet. If you have a public/private key pair set up already, you can still login from the outside with that.

You can also log in with your password from inside the internal network, for example if you connect by VPN.

If you have not set up a passwordless login yet, we have described how to do that here.

We will notify you if the situation changes.

Best regards
Your HPC Team

Aktualisiert um 10:46 am 13. May 2020 von Jan Steiner

Dear cluster users,

due to increased demand there will be another date for the German-language cluster introduction course this semester. If you want to participate, there are more details on the German-language page for the original announcement.

The next English-language introduction course will take place next semester as usual.

Aktualisiert um 16:41 am 8. May 2020 von Jan Steiner

Dear cluster users,

on May 12, the next cluster introduction course will take place. It will be held as a virtual meeting, take all day and the course language will be German (with slides in English). All our courses alternate between German and English each semester. Switch to the German version of this page for more details and registration info.

Best regards

Your HPC Team

Aktualisiert um 15:03 am 23. April 2020 von Jan Steiner

Dear cluster users,

our new cluster needs a name. Therefore we are asking for your help: send us your best ideas on how the new cluster should be called.

The name should express the following:

  • The variety of architectures (CPU, GPU etc.)
  • The variety of applications (HPC, Data Science, Machine Learning, Worldwide LHC Computing Grid)
  • The variety of users
    • Engineers
    • Natural Scientists
    • Scientists in the humanities
  • That the cluster belongs to the (entire) Uni Siegen

The name should be short and succinct. It can be German or English, but should be pronouncable in both languages. It can be an acronym like HoRUS (Hochleistungsrechner Uni Siegen), but does not have to be one.

Please send your submissions to jan.steiner@uni-siegen.de until May 15, 2020. We will select a favorite from the submissions. The winner will receive a small prize. We reserve the right not to select any of the submissions.

Best regards

Your HPC Team

Aktualisiert um 11:16 am 21. April 2020 von Jan Steiner

Dear cluster users,

due to the Coronavirus pandemic the previous date (end of April) for the installation of the new cluster cannot be kept. We are currently expecting that the cluster will go live at the end of June. We apologize for the inconvenience.

Best regards
Your HPC Team

Aktualisiert um 16:49 am 17. April 2020 von Jan Steiner

Dear cluster users,

in the next few months, the University of Siegen will replace the HorUS cluster with a new and considerably more capable system. According to the current plans, the system will go live at the end of April (the initial plans were for the end of February, this will not be possible, mostly due to delays in the delivery of some components).

Overview of the new system

The system consists of the following compute partitions:

  • 434 nodes in the regular HPC partition, which are equipped with AMD CPUs of type EPYC 7452 and 256 GB of RAM each.
  • OpenStack and Kubernetes partitions (8 and 5 nodes respectively).
  • 2 SMP nodes, each with 4 Intel Xeon 5218 CPUs (Cascade Lake) and 1.5 TB RAM.
  • 10 GPU nodes with a total of 24 nVidia GPUs type Tesla V100 (4×4, 2×2, 4×1 GPUs per node)

The storage capacity is 1 Petabyte of primary hard drive space, additionally there is a burst buffer of SSDs (32 Terabytes) and 48 TB of Object Storage space. The flexible concept allows us to adjust the relative sizes of these storage complexes in the future if necessary.

The high-speed interconnect used throughout the cluster is of type Infiniband HDR100.

The following information represents the current state of planning and may change until the new cluster starts operating.

What will change about access and login?

Like the HoRUS cluster, the new cluster will be available to all members of the University of Siegen. The same cluster address will continue to be used and will point to the new cluster after the end of the transition phase at the latest.

What will be the name of the new cluster?

The cluster does not have a name yet. We will have a naming contest for it soon.

Will the other compute resources also be replaced by the new cluster?

No, the HPE Moonshot HTC system and the recently acquired NEC SX-Aurora Tsubasa vector system (more information about that in the near future) will continue to be available.

How do I get my data from HoRUS to the new cluster?

During the transition phase you will have enough time to copy whatever information you need.

Which operating system will the new cluster use?

The OS will be CentOS 8 (HoRUS currently uses CentOS 7). The job scheduler used will be SLURM, just like on HoRUS.

What software will be available on the new cluster?

There will be a collection of commercial software and non-commercial software for a variety of purposes, similar to the HoRUS cluster. You will also be able to request the installation of additional software, we will decide this on a case-by-case basis.

If you have any other questions, email us at hpc-support@uni-siegen.de

Best regards
Your HPC Team

Aktualisiert um 11:12 am 26. February 2020 von Jan Steiner